Nova 2.0 Omni (Medium) — benchmark results
Provider: Amazon. Released 2025-08-01. Access: API.
Unified ELO 1637 ± 31, rank #412 of 1841 rated models, from 54 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA AIME 2025 | 89.67 | Accuracy (%) | 89.8 |
| AA IFBench | 66.19 | Accuracy (%) | 78 |
| AA LiveCodeBench | 66.03 | Pass@1 (%) | 74.3 |
| AA MMLU-Pro | 80.86 | Accuracy (%) | 72.1 |
| AA TAU-2 Bench | 80.41 | Accuracy (%) | 70.3 |
| AA-LCR | 53.7 | Score (self-reported) | 68.2 |
| AA GPQA Diamond | 75.96 | Accuracy (%) | 63.2 |
| AA Long Context Reasoning | 53.67 | Accuracy (%) | 61.3 |
| Artificial Analysis Intelligence Index | 20.95 | Intelligence Index | 61 |
| AA Global-MMLU-Lite - French | 87.25 | Accuracy (%) | 59.8 |
| AA Global-MMLU-Lite - Indonesian | 86.75 | Accuracy (%) | 59.8 |
| AA Global-MMLU-Lite - Bengali | 82.75 | Accuracy (%) | 58.5 |
Interactive version: theaggregate.ai/model?slug=nova-2-0-omni-medium · How It Works · Data refreshed daily, snapshot 2026-07-25.